Subject Area
Physical Sciences, Computer Science
Abstract
In geophysics, seismic and infrasound observations are routinely employed to constrain the nature and origin of events. Seismoacoustics, as a discipline, is built upon the simultaneous detection and integrated analysis of these data types. This joint approach is critical not only for advancing scientific understanding but also for supporting global monitoring efforts in hazard mitigation and nuclear explosion treaty verification. The data analyzed in this dissertation were recorded by array deployments, which consist of multiple sensors arranged in predetermined configurations to enhance signal detection, resolve directionality, and quantify waveform coherence. Leveraging these array recordings, I introduce novel approaches which combine traditional signal processing techniques with advanced deep learning algorithms to augment signal detection rates, improve event discrimination, and enhance the characterization of infrasound phases. The dissertation begins with the development of Cardinal, an open-source multifrequency array processing software for seismic and infrasound data. Cardinal integrates a custom convolutional transformer model to predict optimal array configurations across sequential frequency bands, providing a more comprehensive framework for array analysis. The following chapter presents the development of a multimodal deep neural network that leverages adaptive gating to fuse seismic spectrograms with Cardinal infrasound array processing results. This fusion improves earthquake-explosion discrimination within the Korean Peninsula, surpassing unimodal approaches. The final chapter presents a novel framework for automatic infrasound phase identification, leveraging the latent representations of a pre-trained autoencoder to cluster distinct phases without requiring labeled data. Collectively, these contributions illustrate the potential of combining deep learning with seismoacoustic array data to advance geophysical research and improve the effectiveness of global monitoring networks.
Degree Date
Winter 2025
Document Type
Dissertation
Degree Name
Ph.D.
Department
Earth Sciences
Advisor
Stephen Arrowsmith
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Recommended Citation
Ronac Giannone, Miro, "Advancing the Characterization of Geophysical Signals through Array Processing and Artificial Intelligence" (2025). Earth Sciences Theses and Dissertations. 40.
https://scholar.smu.edu/hum_sci_earthsciences_etds/40
